Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wenhaochai/claude-plugins --skill plotgit clone --depth 1 https://github.com/wenhaochai/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wenhaochai/claude-plugins/plot)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/plot"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/plot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/plot"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/plot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00103 | $0.04590 |
| Opus 5.5 | $0.00041 | $0.01836 |
| Sonnet 5.5 | $0.00021 | $0.00918 |
| Haiku 4.5 | $0.00010 | $0.00459 |
Grade A, and why
plot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plot
style.py (with fonts/) and two examples: example.py, a 2x2 grid of best-so-far step charts, and
example_card.py, Epoch's 4:5 social card (a log-log line with a scenario band, labelled points and
ranges). Copy style.py, fonts/ and the closer example next to your script,
and start from the example.
from style import *
apply_style()
fig, axes = canvas(rows, cols, width=WIDTH_TEXT, panel_height=1.35, title=None,
legend=[('Model A', BLUE), ('Model B', LIGHT)], quantity='Throughput (MB/s)')
ax.plot(...) # or ax.step / ax.bar
nice_y(ax, lo, hi) # the y range, round steps, the values on their grid lines
room(ax) # then x room: past the y values, and past the last grid line
panel_label(ax, 'Setting A') # the panel's name inside it, on a white ground
save(fig, HERE / 'name') # name.pdf + name.png, fitted, raises on text off the canvas
Epoch's other forms are options of the same calls; their docstrings give the details.
| Form | How |
|---|---|
| Subtitle, footnote | canvas(subtitle=..., note=..., note_style='italic') |
| Legend placement | legend_loc='row', 'right', 'inline' (on the quantity's row) or 'column' (with legend_title) |
| Legend swatches | (name, colour, kind), kind 'line', 'dash', 'dot', 'ring', 'box' or 'ci' |
| Export ticks | canvas(ticks='left'), then y_values(ax, ticks, fmt): values left of the panel on tick marks |
| Scatter points | dots(ax, x, y, colour): a translucent fill in a solid edge |
| Annotation | callout(ax, text_xy, target_xy, lines): a note with a curved arrow |
| Direct labels | end_labels(ax, [(y_end, name, colour), ...]): line names at their ends, spread apart |
| Web-canvas charts | title_pt, tick_pt, note_pt, side=0.10 (see rule 5) |
| 16:9 cover | canvas(width=WIDTH_WIDE, aspect=ASPECT_WIDE, ...): panels fill what the header leaves, a 1600 x 900 PNG; covers and artistic images only (see rule 9) |
| Logo markers | logo(ax, x, y, path): an organisation's logo on a white disc at the point (see rule 10) |
| 4:5 card | canvas(card=True, ...): 3.8 in at 4:5 on grey, a 1600 x 2000 PNG; one chart for a social post (see rule 9) |
| Point labels | callout(ax, (dx, dy), target, [name, value], arrow=False, points=True, relpos=...): the label offset in points, a bare curved leader from where relpos says on its box to 4 pt short of the point; offsets clear any band |
| Log axes | ax.set_xscale('log'), ticks at 1, 3, 10, then y_values(ax, ticks, fmt) and room(ax), which widens in log space |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · +7 lines ae54ac4db3f8
- 13d ago Changed · +5 lines 7fa12e77c8ff
- 14d ago Changed · +14 lines 2df45df9e04e
- 15d ago Changed · +52 lines · +10 tokens per session 3cecf12979e2
- 19d ago Changed · +23 lines ada6eeec4444
- 21d ago Changed · -40 lines · -36 tokens per session b5c41140ccf4
- 1mo ago Changed · +27 lines · -52 tokens per session bfbc402d372d
- 1mo ago Changed · +14 lines d030ce119128
- 1mo ago First seen · 102 lines · 181 tokens per session scan A 8043514b8e84
plot is a skill published in the GitHub repository wenhaochai/claude-plugins (17 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 4,590 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.